Method and device for determining drivable area, electronic equipment and storage medium

Abstract

Embodiments of the present disclosure disclose a method and device for determining a drivable area, electronic equipment and a storage medium, wherein the method comprises: obtaining ultrasonic echo information corresponding to each ultrasonic radar in at least one ultrasonic radar, the ultrasonic echo information comprising echo signals and time information; determining echo distances corresponding to each echo signal based on the ultrasonic echo information; determining a current obstacle point set based on the echo distances corresponding to each echo signal; determining a drivable area contour point set based on the current obstacle point set; and determining a drivable area based on the drivable area contour point set. Embodiments of the present disclosure improve the accuracy and reliability of the drivable area detection based on ultrasonic radar, and since the ultrasonic radar has strong ranging capability in a short distance range and is less affected by light, rain, fog and other environments, the detection accuracy of the short distance drivable area can be effectively improved, and the problem of low detection accuracy of the surround-view camera in a short distance is solved.

Description

Technical Field

[0001] This disclosure relates to driver assistance technology, and in particular to a method, apparatus, electronic device, and storage medium for determining a drivable area. Background Technology

[0002] In developing this disclosure, the inventors discovered that free space detection is a crucial component of intelligent parking assistance systems. Free space detection identifies obstacles and drivable areas around the vehicle for path planning and control during the parking phase. In related technologies, free space detection typically relies on surround-view cameras to capture images of the vehicle's surroundings. However, surround-view cameras suffer from poor accuracy in measuring distances to nearby obstacles and have blind spots, resulting in low accuracy in free space detection. Summary of the Invention

[0003] To address the aforementioned technical problems, such as low accuracy in drivable area detection, embodiments of this disclosure provide a method, apparatus, electronic device, and storage medium for determining drivable areas, thereby improving the accuracy, reliability, and detection precision of drivable areas.

[0004] The first aspect of this disclosure provides a method for determining a drivable area, comprising: acquiring ultrasonic echo information corresponding to each of at least one ultrasonic radar, the ultrasonic echo information including echo signal and time information; determining an echo distance corresponding to each echo signal based on the ultrasonic echo information; determining a current set of obstacle points based on the echo distance corresponding to each echo signal; determining a drivable area contour point set based on the current set of obstacle points; and determining a drivable area based on the drivable area contour point set.

[0005] A second aspect of this disclosure provides an apparatus for determining a drivable area, comprising: a first acquisition module for acquiring ultrasonic echo information corresponding to each of at least one ultrasonic radar, the ultrasonic echo information including echo signals and time information; a first processing module for determining echo distances corresponding to each echo signal based on the ultrasonic echo information; a second processing module for determining a current set of obstacle points based on the echo distances corresponding to each echo signal; a third processing module for determining a drivable area contour point set based on the current set of obstacle points; and a fourth processing module for determining a drivable area based on the drivable area contour point set.

[0006] A third aspect of this disclosure provides a computer-readable storage medium storing a computer program for performing the method for determining a drivable area as described in any of the above embodiments of this disclosure.

[0007] A fourth aspect of this disclosure provides an electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the method for determining a drivable area as described in any of the above embodiments of this disclosure.

[0008] A fifth aspect of this disclosure provides a computer program product that, when instructions in the computer program product are executed by a processor, performs the method for determining a drivable region as described in any of the above embodiments of this disclosure.

[0009] Based on the drivable area determination method, apparatus, electronic device, and storage medium provided in the above embodiments of this disclosure, the current obstacle point set is determined based on the ultrasonic echo information of ultrasonic radar. Since the ultrasonic echo information includes the original echo signal and time information, the original echo signal can include the echo signals of obstacle points in the overlapping area of ​​adjacent ultrasonic radars and the echo signals of obstacle points in the non-overlapping area. Therefore, it can take into account both the obstacle points in the overlapping area and the obstacle points in the non-overlapping area of ​​adjacent ultrasonic radars, improving the effectiveness of the current obstacle point set. Furthermore, based on the distribution characteristics of the current obstacle point set, the drivable area contour point set can be determined, which can improve the accuracy of the drivable area contour point set. This, in turn, improves the accuracy and reliability of the drivable area determined based on the drivable area contour point set, realizing accurate and reliable detection of drivable areas based on ultrasonic radar. Moreover, since ultrasonic radar has strong ranging capability in the short range and is less affected by environmental factors such as light, rain, and fog, it can effectively improve the detection accuracy of drivable areas at close range, solving the problem of low detection accuracy of surround-view cameras at close range. Attached Figure Description

[0010] Figure 1 This is an exemplary application scenario of the method for determining the drivable area provided in this disclosure;

[0011] Figure 2 This is a flowchart illustrating a method for determining a drivable area provided in an exemplary embodiment of this disclosure;

[0012] Figure 3 This is a flowchart illustrating a method for determining a drivable area provided in another exemplary embodiment of this disclosure;

[0013] Figure 4 This is a schematic diagram illustrating the principle of the triangulation method provided in an exemplary embodiment of this disclosure;

[0014] Figure 5 This is a flowchart illustrating step 2033 provided in an exemplary embodiment of this disclosure;

[0015] Figure 6 This is a schematic diagram of the radar coordinate system of an ultrasonic radar provided in an exemplary embodiment of this disclosure;

[0016] Figure 7 This is a schematic diagram illustrating the principle of determining the second obstacle point provided in an exemplary embodiment of this disclosure;

[0017] Figure 8 This is a schematic diagram illustrating the principle of determining the second obstacle point provided in another exemplary embodiment of this disclosure;

[0018] Figure 9 This is a schematic diagram illustrating the principle of line aggregation and line splitting provided in an exemplary embodiment of this disclosure;

[0019] Figure 10 This is a flowchart illustrating step 2043 provided in an exemplary embodiment of this disclosure;

[0020] Figure 11 This is a flowchart illustrating step 204 provided in an exemplary embodiment of the present disclosure;

[0021] Figure 12 This is a schematic diagram illustrating the principle of determining the third contour point set provided in an exemplary embodiment of this disclosure;

[0022] Figure 13 This is a schematic diagram of an ultrasonic grid map provided in an exemplary embodiment of the present disclosure;

[0023] Figure 14 This is a schematic diagram of the structure of a device for determining a drivable area provided in an exemplary embodiment of this disclosure;

[0024] Figure 15 This is a schematic diagram of the structure of a device for determining a drivable area provided in another exemplary embodiment of this disclosure;

[0025] Figure 16 This is a schematic diagram of the structure of one application embodiment of the electronic device disclosed herein. Detailed Implementation

[0026] To explain this disclosure, exemplary embodiments of the disclosure will now be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the disclosure, and not all of them. It should be understood that the disclosure is not limited to exemplary embodiments.

[0027] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0028] This disclosure outlines

[0029] In developing this disclosure, the inventors discovered that free space detection is a crucial component of intelligent parking assistance systems. Free space detection identifies obstacles and drivable areas around the vehicle for path planning and control during the parking phase. In related technologies, free space detection typically relies on surround-view cameras to capture images of the vehicle's surroundings. However, surround-view cameras suffer from poor accuracy in measuring distances to nearby obstacles and have blind spots, resulting in low accuracy in free space detection.

[0030] Exemplary Overview

[0031] Figure 1 This is an exemplary application scenario of the method for determining the drivable area provided in this disclosure.

[0032] In parking scenarios, one or more ultrasonic sensor systems (USS) installed on the vehicle can scan the surrounding environment to obtain ultrasonic echo information corresponding to each ultrasonic sensor. This information is used to determine the vehicle's drivable area, providing accurate and effective drivable area data for path planning and control in intelligent parking-assisted driving. The ultrasonic echo information can include echo signal and time information. Using the drivable area determination method disclosed herein, the echo distance corresponding to each echo signal can be determined based on the ultrasonic echo information; the current obstacle point set can be determined based on the echo distance corresponding to each echo signal; the drivable area contour point set can be determined based on the current obstacle point set; and the drivable area can be determined based on the drivable area contour point set. Since ultrasonic echo information includes both the original echo signal and time information, the original echo signal can include the echo signals of obstacle points in the overlapping area of ​​adjacent ultrasonic radars as well as the echo signals of obstacle points in the non-overlapping area. Therefore, it can take into account obstacle points in both the overlapping and non-overlapping areas of adjacent ultrasonic radars, improving the effectiveness of the current obstacle point set. Furthermore, based on the distribution characteristics of the current obstacle point set, the drivable area contour point set can be determined, which can improve the accuracy of the drivable area contour point set. This, in turn, improves the accuracy and reliability of the drivable area determined based on the drivable area contour point set, realizing accurate and reliable detection of drivable areas based on ultrasonic radar. Moreover, since ultrasonic radar has strong ranging capabilities in the short range and is less affected by environmental factors such as light, rain, and fog, it can effectively improve the detection accuracy of drivable areas at close range, solving the problem of low detection accuracy of surround-view cameras at close range.

[0033] In optional embodiments, the drivable area determined by the drivable area determination method of this disclosure can be used as a supplement to the drivable area determined based on the surround view camera, in order to improve the detection accuracy of the drivable area at close range and make up for the shortcomings of the low detection accuracy of the surround view camera at close range.

[0034] The method disclosed herein is not limited to the parking scenario described above, but can also be applied to any other scenario that requires determining a drivable area, such as driving scenarios, without any specific limitation.

[0035] Exemplary methods

[0036] Figure 2 This is a flowchart illustrating a method for determining a drivable area provided in an exemplary embodiment of this disclosure. This embodiment can be applied to electronic devices, specifically, for example, on an in-vehicle computing platform. Figure 2 As shown, it includes the following steps:

[0037] Step 201: Obtain the ultrasonic echo information corresponding to each ultrasonic radar in at least one ultrasonic radar. The ultrasonic echo information includes echo signal and time information.

[0038] The number of ultrasonic radars can be set according to actual needs. For example, an intelligent parking assistance system may have 12 ultrasonic radars: 6 at the front and 6 at the rear. The specific placement can be determined based on requirements. The echo signal is the reflected wave from an obstacle encountered by the ultrasonic radar after it emits an ultrasonic wave. Time information can include the time of ultrasonic wave transmission and the time of echo signal reception, or the time difference between the transmission and reception of the echo signal; the specific timing is not limited. The working principle of ultrasonic radar is as follows: the transmitter emits ultrasonic waves in a certain direction, recording the transmission time or starting a timer at the moment of transmission. The ultrasonic waves propagate through the air, returning immediately upon encountering an obstacle. The receiver of the ultrasonic radar receives the reflected wave, recording the reception time or immediately stopping the timer, thus obtaining time information.

[0039] Step 202: Based on the ultrasonic echo information, determine the echo distance corresponding to each echo signal.

[0040] The echo distance can be determined based on the time information corresponding to the echo signal and the speed of ultrasonic wave propagation in the air. For example, the time difference t between ultrasonic wave transmission and reception can be determined based on the time information. The speed of ultrasonic wave propagation is fixed and is expressed as v. Then the echo distance can be expressed as s = vt / 2.

[0041] It should be noted that for an ultrasonic radar, the echo signal it receives can be the echo signal of the ultrasonic wave it emits, or the echo signal of the ultrasonic wave emitted by other adjacent ultrasonic radars. For example, if the scanning ranges of adjacent ultrasonic radars A and B overlap, and there is an obstacle in this overlapping area, both A and B can receive the echo signal of the ultrasonic wave emitted by A encountering the obstacle. By analyzing the echo signal, B can obtain the emission time, and by combining it with its recorded reception time, it can determine the echo distance corresponding to the echo signal.

[0042] Step 203: Determine the current obstacle point set based on the echo distance corresponding to each echo signal.

[0043] Since the echo signal is the ultrasonic wave that returns when it encounters an obstacle, the echo distance corresponding to the echo signal represents the distance to the obstacle. Based on the echo distance and the scanning range of the ultrasonic radar, the set of points of the scanned obstacle can be determined through methods such as triangulation, and this set of points can be used as the current obstacle point set.

[0044] For example, if two adjacent ultrasonic radars receive echo signals from the same obstacle in an overlapping area, the obstacle's location can be determined as an obstacle point based on triangulation. For the echo distance of obstacles in non-overlapping areas, at least one obstacle point can be obtained by sampling points at the same distance from the echo distance within the ultrasonic radar's scanning range.

[0045] Step 204: Determine the drivable area contour point set based on the current obstacle point set.

[0046] The drivable area contour point set refers to the set of points on the contour of the vehicle's drivable area. The drivable area refers to the unobstructed area where the vehicle can drive. The current obstacle point set represents the set of obstacle boundary points within the current sensing range of the ultrasonic radar; therefore, the drivable area contour point set can be determined based on the current obstacle point set.

[0047] In one optional embodiment, the points in the current obstacle point set can be points in the vehicle coordinate system, and the points in the drivable area outline point set can be points in the world coordinate system or the map coordinate system, which can be set according to actual needs.

[0048] In one alternative embodiment, the points in the drivable area outline point set can also be points in the vehicle coordinate system. When merging with historical drivable areas, such as when incrementally constructing an ultrasonic grid map, they can be converted to a unified world coordinate system or map coordinate system. The specific conversion is not limited.

[0049] Step 205: Determine the drivable area based on the set of drivable area contour points.

[0050] Among them, the drivable area refers to the unobstructed area where vehicles can drive. After determining the drivable area contour point set, the drivable area can be determined based on the drivable area contour point set. Specifically, the area enclosed by the contour line formed by the drivable area contour point set is the drivable area.

[0051] The method for determining drivable areas provided in this embodiment determines the current obstacle point set based on ultrasonic echo information from ultrasonic radar. Since ultrasonic echo information includes the original echo signal and time information, the original echo signal can include the echo signals of obstacle points in the overlapping areas of adjacent ultrasonic radars as well as the echo signals of obstacle points in non-overlapping areas. Therefore, it can take into account both obstacle points in the overlapping areas and obstacle points in non-overlapping areas of adjacent ultrasonic radars, improving the effectiveness of the current obstacle point set. Furthermore, based on the distribution characteristics of the current obstacle point set, the drivable area contour point set can be determined, which can improve the accuracy of the drivable area contour point set. This, in turn, improves the accuracy and reliability of the drivable area determined based on the drivable area contour point set, achieving accurate and reliable detection of drivable areas based on ultrasonic radar. Moreover, since ultrasonic radar has strong ranging capabilities in the short range and is less affected by environmental factors such as light, rain, and fog, it can effectively improve the detection accuracy of drivable areas at close range, solving the problem of low detection accuracy of surround-view cameras at close range.

[0052] Figure 3 This is a flowchart illustrating a method for determining a drivable area provided in another exemplary embodiment of this disclosure.

[0053] In an optional embodiment, step 203 may include the following steps:

[0054] Step 2031: Based on the echo distance and time information corresponding to each echo signal, determine the echo distance group belonging to the same obstacle point. Each echo distance group includes the first echo distance and the second echo distance belonging to the same echo point.

[0055] In this context, for two adjacent ultrasonic radars, obstacles in the overlapping area of ​​their scanning ranges will cause the ultrasonic waves emitted by one ultrasonic radar to be received as echo signals by both ultrasonic radars. In this case, the echo distances corresponding to these two echo signals can be referred to as the first echo distance and the second echo distance, respectively. These first and second echo distances constitute the echo distance group belonging to the same obstacle point. Echo signals belonging to the same obstacle point can be determined based on the relationship and timing information between the ultrasonic radars receiving the echo signals. For example, two adjacent ultrasonic radars A and B can be configured not to emit ultrasonic waves simultaneously; when A emits, B does not. If the emission time of one echo signal received by A is the same as the emission time of one echo signal received by B, it can be determined that these two echo signals belong to the same obstacle point. In practical applications, echo signals belonging to the same obstacle point can also be determined through any other possible methods, which can be set according to actual needs. This disclosure does not impose any limitations on this method.

[0056] Step 2032: Based on the echo distance group belonging to the same obstacle point, determine the first obstacle point corresponding to the echo distance group.

[0057] The first obstacle point can be determined using triangulation. The same number of first obstacle points can be determined based on the number of echo distance groups.

[0058] Step 2033: Based on the third echo distance (excluding the echo distance group) among all echo distances, determine the second obstacle point corresponding to the third echo distance.

[0059] For obstacles not located in the overlapping area of ​​adjacent ultrasonic radars, the echo signal received by the transmitting ultrasonic radar does not correspond to any echo signal belonging to the same obstacle point. Therefore, there is no corresponding echo distance group. The echo distances corresponding to these echo signals are called the third echo distances. For any given third echo distance, one or more second obstacle points can be identified. For any ultrasonic radar, the second obstacle points within its scanning range can be determined based on the ultrasonic radar's scanning range and the third echo distance. For example, one or more points within the ultrasonic radar's scanning range that are at the third echo distance from the ultrasonic radar can be collected as second obstacle points.

[0060] Step 2034: Determine the current obstacle point set based on each first obstacle point and each second obstacle point.

[0061] In this process, after obtaining each first obstacle point and each second obstacle point, the set of points formed by each first obstacle point and each second obstacle point can be used as the current obstacle point set.

[0062] This embodiment determines the current obstacle point set by identifying obstacle points in the overlapping areas of adjacent ultrasonic radars and obstacle points in the non-overlapping areas of ultrasonic radars, thus providing effective data for determining the contour point set of the drivable area.

[0063] In an optional embodiment, step 2032, determining the first obstacle point corresponding to the echo distance group based on the echo distance group belonging to the same obstacle point, includes:

[0064] For any echo distance group, based on the first echo distance, the second echo distance, the first position of the ultrasonic radar corresponding to the first echo distance, and the second position of the ultrasonic radar corresponding to the second echo distance, the triangulation method is used to determine the first obstacle point corresponding to the echo distance group. The first position and the second position are the positions in the vehicle coordinate system.

[0065] For example, Figure 4 This is a schematic diagram illustrating the principle of the triangulation method provided in an exemplary embodiment of this disclosure. In this example, six ultrasonic radars (A, B, C, D, E, and F) are installed at the front of the vehicle. Taking A and B as examples, if an obstacle O exists in the overlapping area of ​​their scanning ranges, an echo distance set can be obtained. AO represents the first echo distance, and BO represents the second echo distance. The first position of A and the second position of B can be determined based on the vehicle's position. The relative positions between A and B are pre-obtained and stored, and may include the lateral distance ABx, longitudinal distance ABy, straight-line distance AB, and the angle α between AB and the longitudinal direction. xy is a preset reference coordinate system, where the x-axis direction represents the lateral direction and the y-axis direction represents the longitudinal direction. The angle between BO and the longitudinal direction is represented by △p, and the angle between BO and AB is represented by b. The position of O can be determined according to the following formula:

[0066]

[0067]

[0068] cosΔp=cosa*cosb+sina*sinb

[0069] AOy=AO*cosΔp

[0070] AOx=AO*sinΔp

[0071] This embodiment can effectively determine obstacle points in the overlapping area of ​​adjacent ultrasonic radars through triangulation, providing accurate and effective obstacle points for determining the current obstacle point set.

[0072] Figure 5 This is a flowchart illustrating step 2033 provided in an exemplary embodiment of this disclosure.

[0073] In an optional embodiment, step 2033, determining the second obstacle point corresponding to the third echo distance based on the third echo distance outside the echo distance group in each echo distance, includes:

[0074] Step 20331: For any third echo distance, within the scanning range of the ultrasonic radar corresponding to the third echo distance, determine the line segment whose horizontal axis coordinate is the same as the third echo distance in the radar coordinate system of the ultrasonic radar.

[0075] In the radar coordinate system, the horizontal axis is the axis along the normal direction of the ultrasonic radar's field of view (FOV).

[0076] For example, Figure 6 This is a schematic diagram of the radar coordinate system of an ultrasonic radar provided in an exemplary embodiment of this disclosure. Here, uss_pos represents the position of the ultrasonic radar, i.e., the origin of the radar coordinate system; x represents the horizontal coordinate axis; y represents the vertical coordinate axis; and the U-shaped region formed by P0-P4 and Q0-Q4 is the scanning range of the ultrasonic radar. PiQi represents a line segment whose horizontal coordinate is the same as the distance to the third echo.

[0077] Step 20332: Based on the preset sampling rules, sample the first number of points on the line segment.

[0078] The preset sampling rules can be set according to actual needs, such as sampling at equal intervals, without any specific limitations. For example, multiple points can be sampled at equal intervals on the PiQi mentioned above.

[0079] Step 20333: Convert the first number of points to the vehicle coordinate system to obtain the second obstacle point corresponding to the third echo distance.

[0080] In order to fuse the points from different ultrasonic radars, the first number of points collected are converted to the vehicle coordinate system to obtain the second obstacle point corresponding to the third echo distance.

[0081] This embodiment determines the line segment whose horizontal axis coordinate is the same as the distance of the third echo in the radar coordinate system within the ultrasonic radar scanning range, and then samples on the line segment to determine the second obstacle point corresponding to the distance of the third echo, thereby further improving the effectiveness and reliability of the current obstacle point set.

[0082] In one alternative embodiment, Figure 7 This is a schematic diagram illustrating the principle of determining a second obstacle point according to an exemplary embodiment of this disclosure. In this example, within the scanning range of the ultrasonic radar, sampling can be performed at equal angular intervals with the origin of the radar coordinate system as the center and the third echo distance d as the radius to obtain the second obstacle point corresponding to the third echo distance.

[0083] In one alternative embodiment, Figure 8 This is a schematic diagram of the principle for determining the second obstacle point provided in another exemplary embodiment of this disclosure. With the origin of the radar coordinate system as the center and the third echo distance as the radius d, two intersection points Pj and Qj of the arc and the ultrasonic radar scanning boundary are determined. In order to ensure the safety of the drivable area, sampling is performed on the line segment connecting Pj and Qj to obtain the second obstacle point corresponding to the third echo distance.

[0084] In an optional embodiment, step 204, determining the drivable area contour point set based on the current obstacle point set, includes:

[0085] Step 2041: Transform the current obstacle point set to the world coordinate system to obtain the target obstacle point set in the world coordinate system corresponding to the current obstacle point set.

[0086] The current obstacle point set is a point set in the vehicle coordinate system. Since the position of the origin of the vehicle coordinate system is different at different times, in order to merge the drivable area contour point set of the current obstacle point set with the historical drivable area contour point set, the obtained obstacle point set is transformed to the world coordinate system in each time frame. Similarly, the current obstacle point set is transformed to the world coordinate system to obtain the target obstacle point set in the world coordinate system corresponding to the current obstacle point set.

[0087] Step 2042: Based on the previous obstacle clustering results, perform incremental obstacle clustering on the target obstacle point set to obtain the first point set corresponding to at least one target obstacle. The previous obstacle clustering results are the result of clustering based on the previously obtained obstacle point set.

[0088] The previously obtained obstacle point set can include obstacle point sets from all previous time frames or the most recent preset number of time frames, which can be set according to actual needs. Since the scanning of an obstacle may not be completed within a time frame, and only a part of the obstacle is scanned, the obstacle point set obtained in subsequent time frames may also include the remaining obstacle points. Therefore, by combining the previous obstacle clustering results, incremental obstacle clustering is performed on the target obstacle point set, so as to gradually obtain the complete obstacle point set corresponding to the target obstacle. For the same target obstacle, the obstacle point set corresponding to the target obstacle obtained by clustering in each time frame is called the first point set.

[0089] Step 2043: Determine the drivable area contour point set based on the first point set corresponding to each target obstacle.

[0090] In an alternative embodiment, the first set of points corresponding to each target obstacle can be used as the set of points representing the drivable area contour.

[0091] In an optional embodiment, the side corner points of the target obstacles can be determined based on the first set of points corresponding to each target obstacle, and the drivable area contour point set can be determined based on the side corner points of each target obstacle, so as to reduce the number of points in the drivable area contour point set.

[0092] In one optional embodiment, incremental obstacle clustering can determine whether points in the target obstacle point set belong to the same target obstacle in the previous obstacle clustering results by considering the relationships between points in the target obstacle point set and points in the previous obstacle clustering results. Specifically, for example, points within a certain range are determined to belong to the same target obstacle.

[0093] In one optional embodiment, during the clustering process, distance matching can be performed based on Euclidean distance, associating points within a certain distance range as belonging to the same class. To improve the descriptiveness of obstacle boundaries, virtual boundaries can be generated through single-line, two-segment, and three-segment clustering. Specifically, the aggregation and splitting of line segments can be performed based on the state of the target obstacle point set after incremental aggregation (e.g., the change in the slope of the line containing adjacent points compared to the slope of the previously clustered points) and the state of the previous obstacle clustering results.

[0094] For example, Figure 9 This is a schematic diagram illustrating the principle of line aggregation and line splitting provided in an exemplary embodiment of this disclosure. The state after incremental aggregation of the target obstacle point set can include three cases: single-line aggregation, two-segment line aggregation, and three-segment line aggregation. If the change between adjacent slopes is within a preset threshold range, it can be determined to be a single-line aggregation state. If the change between two adjacent slopes exceeds the preset threshold, it indicates that the line state has changed. If only one change occurs, it is determined to be a two-segment line aggregation, requiring line splitting (two-segment line splitting) to divide the aggregation point into two line segments. Similarly, when the line state changes twice, it is determined to be a three-segment line aggregation, requiring three-segment line splitting to divide the three-segment line aggregation point into three line segments to describe the boundary of the target obstacle, providing a basis for determining the subsequent drivable area contour point set.

[0095] This embodiment uses incremental obstacle clustering based on previous obstacle clustering results to effectively determine the obstacle point set of the same target obstacle in multiple consecutive frame scans. This provides accurate and effective point set data for subsequent reduction of the number of points based on obstacle surface features, thereby further improving the accuracy and stability of the drivable area based on multi-frame fusion.

[0096] Figure 10 This is a flowchart illustrating step 2043 provided in an exemplary embodiment of this disclosure.

[0097] In an optional embodiment, step 2043, determining the drivable area contour point set based on the first point set corresponding to each target obstacle, includes:

[0098] Step 20431: For any first ultrasonic radar among the ultrasonic radars, in response to the first ultrasonic radar corresponding to at least one target obstacle, determine the first side corner point and the second side corner point corresponding to each target obstacle based on the first point set corresponding to each target obstacle corresponding to the first ultrasonic radar.

[0099] The first ultrasonic radar can be any ultrasonic radar among all ultrasonic radars. The first and second corner points can be based on... Figure 9 The results of unidirectional aggregation, two-segment splitting, and three-segment splitting shown can be determined. For example, the leftmost point of the target obstacle can be taken as the first side corner point, and the rightmost point can be taken as the second side corner point.

[0100] Step 20432: Take the first side corner point and the second side corner point corresponding to each target obstacle as the first contour point set, and determine the label corresponding to the first contour point set.

[0101] The label corresponding to the first contour point set is used to characterize the type of the first contour point set. This type can include a first type and a second type. The first type can be an obstacle type, and the second type can be a passable type. The specific representation can be set according to actual needs. Since the first contour point set is determined based on the side corner points of the target obstacle, the label corresponding to the first contour point set is the first type, which is used for the subsequent construction of the ultrasonic grid map.

[0102] In one optional embodiment, for the case of two line segments, in addition to using the leftmost point as the first corner point and the rightmost point as the second corner point, the intersection of the two line segments can also be used as the first midpoint, which, together with the first and second corner points, forms the first contour point set. Similarly, for the case of three line segments, the two intersection points between the three line segments can be used as the second and third midpoints, respectively, which, together with the first and second corner points, form the first contour point set. The specific settings can be configured according to actual needs.

[0103] Step 20433: Based on the first contour point set and the corresponding label of the first contour point set, determine the drivable area contour point subset corresponding to the first ultrasonic radar.

[0104] The subset of drivable area contour points corresponding to the first ultrasonic radar includes all points in the first contour point set and the corresponding labels. Based on this, the subset of drivable area contour points corresponding to each ultrasonic radar can be obtained.

[0105] Step 20434: Determine the drivable area contour point set based on the subset of drivable area contour points corresponding to each ultrasonic radar.

[0106] This embodiment determines the first and second side corner points corresponding to each target obstacle as the first contour point set corresponding to the ultrasonic radar, which can effectively reduce the number of points and improve processing efficiency.

[0107] Figure 11 This is a flowchart illustrating step 204 provided in an exemplary embodiment of the present disclosure.

[0108] In an optional embodiment, step 204 further includes:

[0109] Step 20441: For any first ultrasonic radar among all ultrasonic radars, determine the positional relationship between the first ultrasonic radar and the other ultrasonic radars.

[0110] When multiple ultrasonic radars are arranged adjacently, if one of the ultrasonic radars is installed on either side of the other ultrasonic radars, since one side does not have an adjacent ultrasonic radar, the scanning boundary point of that side needs to be used as the current drivable area contour point to determine the current drivable area contour point set. Therefore, for any first ultrasonic radar, it is necessary to determine the positional relationship between the first ultrasonic radar and the other ultrasonic radars. See [reference needed]. Figure 4 The positional relationship of the six ultrasonic radars AF is shown in the figure, with E and F located on the first (left) and second (right) sides of each ultrasonic radar, respectively.

[0111] Step 20442: In response to the first ultrasonic radar being located on the first or second side of each of the other ultrasonic radars, the set of scanning boundary points on the side of the first ultrasonic radar away from each of the other ultrasonic radars is taken as the second contour point set, and the label corresponding to the second contour point set is determined.

[0112] Wherein, see scan boundary. Figure 6 The left boundary line where P0-P4 are located and the right boundary line where Q0-Q4 are located. Since the second contour point set is a scan boundary point set, which is limited by the scanning range of the ultrasonic radar and has no obstacles, the label corresponding to the second contour point set can be set to the second type (passable type), for example... Figure 4 The left scan boundary of E and the right scan boundary of F both represent the road sections on either side of the vehicle.

[0113] Step 20443: In response to the first ultrasonic radar being located between at least two other ultrasonic radars and the existence of a first obstacle point with triangulation within the scanning range of the first ultrasonic radar, a first straight line passing through the first obstacle point and perpendicular to the normal of the field of view of the first ultrasonic radar is determined based on the first obstacle point.

[0114] The normal to the field of view of the first ultrasonic radar is the straight line containing the x-axis of the radar coordinate system of the first ultrasonic radar. If the first ultrasonic radar is located between at least two other ultrasonic radars, such as the aforementioned four ultrasonic radars A, B, C, and D, there may be a first obstacle point in the overlapping area due to the overlapping area with the adjacent ultrasonic radars. If there is a first obstacle point, the first straight line can be determined based on the first obstacle point and the normal to the field of view of the first ultrasonic radar.

[0115] Step 20444: Based on the first straight line, determine the first intersection point of the first straight line and the normal of the field of view of the first ultrasonic radar, and the second intersection point of the first straight line and the scanning boundary of the first ultrasonic radar near the first obstacle point.

[0116] The scanning boundary near the first obstacle point refers to the boundary of the overlapping area where the first obstacle point is located. For example, if A is the first ultrasonic radar and the first obstacle point is the overlapping area of ​​A and B, then the scanning boundary of the first ultrasonic radar near the first obstacle point refers to the right boundary of A.

[0117] Step 20445: Take the first intersection point and the second intersection point as the third contour point set, and determine the label corresponding to the third contour point set.

[0118] The first and second intersection points are determined based on the first obstacle point, therefore the label corresponding to the third contour point set is set to the first type (obstacle type).

[0119] If the first ultrasonic radar is located on the first or second side of each of the other ultrasonic radars, then step 20433, based on the first contour point set and the labels corresponding to the first contour point set, determines the subset of drivable area contour points corresponding to the first ultrasonic radar, including:

[0120] Step 20433a: Based on the first contour point set, the label corresponding to the first contour point set, the second contour point set, and the label corresponding to the second contour point set, determine the drivable area contour point subset corresponding to the first ultrasonic radar.

[0121] If the first ultrasonic radar is located between at least two other ultrasonic radars, then step 20433, based on the first contour point set and the labels corresponding to the first contour point set, determines the subset of drivable area contour points corresponding to the first ultrasonic radar, including:

[0122] Step 20433b: Based on the first contour point set, the label corresponding to the first contour point set, the third contour point set, and the label corresponding to the third contour point set, determine the drivable area contour point subset corresponding to the first ultrasonic radar.

[0123] Based on the above process, the subset of drivable area contour points corresponding to each ultrasonic radar can be determined.

[0124] For example, Figure 12 This is a schematic diagram illustrating the principle of determining the third contour point set provided in an exemplary embodiment of this disclosure. Wherein, uss-xy represents the radar coordinate system of the first ultrasonic radar, and x and y respectively represent the first ultrasonic radar (corresponding to...). Figure 4 In the radar coordinate system of A), the x and y axes are defined, lp represents the first obstacle point, the dashed line containing lp represents the first straight line, and P and Q represent the first and second intersection points, respectively. R1 and R2 represent the first and second side corner points of the target obstacle obj (the line segment between R1 and R2), respectively. vcs-xy represents the vehicle coordinate system.

[0125] This embodiment determines a second set of contour points and corresponding labels or a third set of contour points and corresponding labels based on the different locations of the ultrasonic radar. These are used together with the first set of contour points and corresponding labels to determine the drivable area contour point subsets corresponding to each ultrasonic radar, effectively improving the accuracy and effectiveness of the drivable area contour point subsets.

[0126] In one optional embodiment, the label corresponding to the first contour point set is of the first type; the label corresponding to the second contour point set is of the second type; and the label corresponding to the third contour point set is of the first type.

[0127] Step 20433a, which determines the subset of drivable area contour points corresponding to the first ultrasonic radar based on the first contour point set, the labels corresponding to the first contour point set, the second contour point set, and the labels corresponding to the second contour point set, includes:

[0128] Based on the label corresponding to the first contour point set being of the first type, the state of each contour point in the first contour point set is determined as the first state; based on the label corresponding to the second contour point set being of the second type, the state of each contour point in the second contour point set is determined as the second state; the contour points in the first contour point set and their corresponding first states, and the contour points in the second contour point set and their corresponding second states, are combined to form a subset of drivable area contour points corresponding to the first ultrasonic radar.

[0129] The first state can be occupied, and the second state can be free. The first and second states are used for the subsequent construction of the ultrasonic raster map.

[0130] This embodiment determines the state of each contour point, providing accurate and effective data for the incremental construction of subsequent ultrasonic grid maps.

[0131] In an optional embodiment, step 20433b, which determines the subset of drivable area contour points corresponding to the first ultrasonic radar based on the first contour point set, the labels corresponding to the first contour point set, the third contour point set, and the labels corresponding to the third contour point set, includes:

[0132] Based on the label corresponding to the first contour point set being of the first type, the state of each contour point in the first contour point set is determined as the first state; based on the label corresponding to the third contour point set being of the first type, the state of each contour point in the third contour point set is determined as the first state; the contour points in the first contour point set and their corresponding first states, and the contour points in the third contour point set and their corresponding first states, are combined to form a subset of drivable area contour points corresponding to the first ultrasonic radar.

[0133] The specific operating principle of this step is similar to that of step 20433a mentioned above, and will not be repeated here.

[0134] In an optional embodiment, after determining the drivable area contour point set based on the current obstacle point set in step 204, the method further includes:

[0135] Step 301: Based on the set of contour points of the drivable area, update the previously obtained ultrasonic grid map to obtain an updated ultrasonic grid map.

[0136] The ultrasonic grid map obtained earlier is incrementally constructed based on the previously acquired set of drivable area contour points. This map includes each grid in a grid coordinate system and its corresponding state. The state of each grid indicates whether the area within that grid is drivable or occupied. Specifically, the ultrasonic grid map can be incrementally updated based on each contour point in the drivable area contour point set and its corresponding state to obtain an updated ultrasonic grid map.

[0137] In one alternative embodiment, the updated ultrasonic grid map can be a grid map within a certain range around the vehicle's current location. For example, a range of 10 meters in front of and behind the vehicle; the specific range can be set according to actual needs. That is, the maintained ultrasonic grid map area changes continuously as the vehicle moves.

[0138] In an alternative embodiment, the updated ultrasonic grid map can be converted to the current vehicle coordinate system for downstream path planning.

[0139] This embodiment can provide an effective basis for downstream path planning by constructing an ultrasonic grid map.

[0140] In an optional embodiment, step 301, which updates the previously obtained ultrasonic grid map based on the drivable area contour point set to obtain an updated ultrasonic grid map, includes:

[0141] Based on the contour points in the drivable area contour point set and the corresponding states of each contour point, the state of the target grid in the ultrasonic grid map is determined. The states corresponding to the contour points include the first state and the second state. Based on the state of the target grid, the previously obtained ultrasonic grid map is updated to obtain the updated ultrasonic grid map.

[0142] The size of each grid cell in the ultrasonic grid map can be set according to actual needs. For example, the size of the maintained ultrasonic grid map is 900*900, which means there are 900*900 grid cells. The current state of each grid cell can be determined by combining the contour points and corresponding states of the previously obtained drivable area contour point set. Specifically, it can be determined based on Bayes' theorem.

[0143] For example, the ultrasonic grid map size is set to 900*900. The state of each grid can include a free state and an occupied state, denoted by 's', where s=1 indicates an occupied state and s=0 indicates a free state. P(s=1) represents the probability of being in the occupied state and P(s=0) represents the probability of being in the free state. The ratio of the two probabilities is used to represent the grid state, as shown below:

[0144] Odd(s) = P(s=1) / P(s=0) Formula 1

[0145] For each grid cell, if a new measurement value z ~ {0, 1} is obtained, this measurement value can be determined based on the previously obtained set of drivable area contour points. For example, by mapping each contour point in the drivable area contour point set to the ultrasonic grid map coordinate system and determining its corresponding target grid cell, the state of the contour point will affect the state of the target grid cell. Therefore, the state of the target grid cell needs to be updated. Let Odd(s|z) represent the state of s under the condition that z occurs, that is:

[0146] Odd(s|z)=P(s=1|z) / P(s=0|z) Formula 2

[0147] Where P(s=1|z) represents the probability that s=1 given that z occurs, and P(s=0|z) represents the probability that s=0 given that z occurs.

[0148] According to Bayes' theorem:

[0149]

[0150]

[0151]

[0152] Where P(z|s=1) represents the probability of z occurring given that s=1 has occurred, and P(z|s=0) represents the probability of z occurring given that s=0 has occurred.

[0153] Taking the logarithm of both sides of formula 5, we get:

[0154]

[0155] Wherein, logOdd(s|z) represents the state value of the target raster. The larger the state value, the greater the probability that the target raster is in an occupied state; the smaller the state value, the less likely that the target raster is in an idle state. Based on this, certain mapping rules can be set to determine the current state of the target raster. For example, a state threshold can be set. When the state value is greater than the state threshold, the target raster is determined to be in an occupied state; otherwise, it is in an idle state. The specific rules can be set according to actual needs, and this disclosure does not limit them.

[0156] The first term on the right side of Formula 6 is related to the measured value. The measured value has only two states: occupied and free. The specific state can be determined based on the aforementioned set of drivable area contour points. Ultimately, each measured value has a corresponding definite state. Assume:

[0157]

[0158]

[0159]

[0160] Wherein, logoccu represents the value of the first term on the right side of formula 6 when the measured value is in the occupied state (i.e., z = 1), logfree represents the value of the first term on the right side of formula 6 when the measured value is in the free state (i.e., z = 0), and logOdd(s) represents the value of the second term on the right side of formula 6. Based on this, and combined with the measured value of each grid cell, the specific state value of logOdd(s|z) can be determined.

[0161] Based on the above principle, the status of each grid in the ultrasonic grid map within a preset range around the vehicle's current location can be updated in real time, thereby obtaining an updated ultrasonic grid map.

[0162] It should be noted that when the points of the drivable area enclosed by the set of drivable area contour points are used as the measurement values ​​of the corresponding target grid in the ultrasonic grid map, the measurement value is in an idle state (z=0).

[0163] For example, Figure 13 This is a schematic diagram of an ultrasonic grid map provided in an exemplary embodiment of this disclosure. Occupied space represents a grid cell in an occupied state, and free space represents a grid cell in an idle state.

[0164] In an optional embodiment, the method for determining the drivable area disclosed herein can also be combined with determining the drivable area based on images acquired by a camera, further improving the accuracy and effectiveness of the determined drivable area.

[0165] The embodiments described above can be implemented individually or in any combination without conflict. The specific implementation can be set according to actual needs, and this disclosure does not limit them.

[0166] Any of the methods for determining a drivable area provided in this disclosure can be executed by any suitable device with data processing capabilities, including but not limited to: terminal devices and servers. Alternatively, any of the methods for determining a drivable area provided in this disclosure can be executed by a processor, such as by a processor executing any of the methods for determining a drivable area mentioned in this disclosure by calling corresponding instructions stored in memory. Further details will not be elaborated below.

[0167] Exemplary device

[0168] Figure 14 This is a schematic diagram of a device for determining a drivable area provided in an exemplary embodiment of this disclosure. The device in this embodiment can be used to implement corresponding method embodiments of this disclosure, such as… Figure 14 The device shown includes: a first acquisition module 501, a first processing module 502, a second processing module 503, a third processing module 504, and a fourth processing module 505.

[0169] The first acquisition module 501 is used to acquire ultrasonic echo information corresponding to each ultrasonic radar in at least one ultrasonic radar. The ultrasonic echo information includes echo signal and time information.

[0170] The first processing module 502 is used to determine the echo distance corresponding to each echo signal based on each ultrasonic echo information.

[0171] The second processing module 503 is used to determine the current set of obstacle points based on the echo distance corresponding to each echo signal.

[0172] The third processing module 504 is used to determine the drivable area contour point set based on the current obstacle point set.

[0173] The fourth processing module 505 is used to determine the drivable area based on the set of drivable area contour points.

[0174] Figure 15 This is a schematic diagram of the structure of a device for determining a drivable area provided in another exemplary embodiment of this disclosure.

[0175] In an optional embodiment, the second processing module 503 includes: a first processing unit 5031, a second processing unit 5032, a third processing unit 5033, and a fourth processing unit 5034.

[0176] The first processing unit 5031 is used to determine the echo distance group belonging to the same obstacle point based on the echo distance corresponding to each echo signal and the time information corresponding to each echo signal. Each echo distance group includes the first echo distance and the second echo distance belonging to the same echo point.

[0177] The second processing unit 5032 is used to determine the first obstacle point corresponding to the echo distance group based on the echo distance group belonging to the same obstacle point.

[0178] The third processing unit 5033 is used to determine the second obstacle point corresponding to the third echo distance based on the third echo distance in each echo distance group other than the echo distance group.

[0179] The fourth processing unit 5034 is used to determine the current set of obstacle points based on each first obstacle point and each second obstacle point.

[0180] In an optional embodiment, the second processing unit 5032 is specifically used for:

[0181] For any echo distance group, based on the first echo distance, the second echo distance, the first position of the ultrasonic radar corresponding to the first echo distance, and the second position of the ultrasonic radar corresponding to the second echo distance, the triangulation method is used to determine the first obstacle point corresponding to the echo distance group. The first position and the second position are the positions in the vehicle coordinate system.

[0182] In an optional embodiment, the third processing unit 5033 is specifically used for:

[0183] For any third echo distance, within the scanning range of the ultrasonic radar corresponding to the third echo distance, determine a line segment whose horizontal axis coordinate is the same as the third echo distance in the radar coordinate system of the ultrasonic radar; based on a preset sampling rule, sample a first number of points on the line segment; transform the first number of points to the vehicle coordinate system to obtain the second obstacle point corresponding to the third echo distance.

[0184] In an optional embodiment, the third processing module 504 includes: a coordinate transformation unit 5041, a clustering unit 5042, and a first determination unit 5043.

[0185] The coordinate transformation unit 5041 is used to transform the current obstacle point set to the world coordinate system to obtain the target obstacle point set in the world coordinate system corresponding to the current obstacle point set.

[0186] Clustering unit 5042 is used to perform incremental obstacle clustering on the target obstacle point set based on the previous obstacle clustering result, to obtain the first point set corresponding to at least one target obstacle respectively. The previous obstacle clustering result is the result of clustering based on the previously obtained obstacle point set.

[0187] The first determining unit 5043 is used to determine the contour point set of the drivable area based on the first point set corresponding to each target obstacle.

[0188] In an optional embodiment, the first determining unit 5043 is specifically used for:

[0189] For any first ultrasonic radar among all ultrasonic radars, in response to the first ultrasonic radar corresponding to at least one target obstacle, based on the first point set corresponding to each target obstacle corresponding to the first ultrasonic radar, the first side corner point and the second side corner point corresponding to each target obstacle are determined respectively; the first side corner point and the second side corner point corresponding to each target obstacle are used as the first contour point set, and the label corresponding to the first contour point set is determined; based on the first contour point set and the label corresponding to the first contour point set, the drivable area contour point subset corresponding to the first ultrasonic radar is determined; based on the drivable area contour point subset corresponding to each ultrasonic radar, the drivable area contour point set is determined.

[0190] In an optional embodiment, the first determining unit 5043 is further configured to:

[0191] For any first ultrasonic radar among all ultrasonic radars, determine the positional relationship between the first ultrasonic radar and the other ultrasonic radars besides the first ultrasonic radar; in response to the first ultrasonic radar being located on the first or second side of each of the other ultrasonic radars, take the scanning boundary point set of the side of the first ultrasonic radar away from each of the other ultrasonic radars as the second contour point set, and determine the label corresponding to the second contour point set; the first determining unit 5043 is specifically used to determine the drivable area contour point subset corresponding to the first ultrasonic radar based on the first contour point set, the label corresponding to the first contour point set, the second contour point set, and the label corresponding to the second contour point set. Alternatively, the first determining unit 5043 is further used to: in response to the first ultrasonic radar being located between at least two other ultrasonic radars, and a first obstacle point with triangulation existing within the scanning range of the first ultrasonic radar, determine a first straight line passing through the first obstacle point and perpendicular to the field angle normal of the first ultrasonic radar based on the first obstacle point; based on the first straight line, determine the first intersection point of the first straight line and the field angle normal of the first ultrasonic radar, and the second intersection point of the first straight line and the scanning boundary of the first ultrasonic radar near the first obstacle point; take the first intersection point and the second intersection point as the third contour point set, and determine the label corresponding to the third contour point set. Accordingly, the first determining unit 5043 is specifically used to: determine the subset of drivable area contour points corresponding to the first ultrasonic radar based on the first contour point set, the label corresponding to the first contour point set, the third contour point set, and the label corresponding to the third contour point set.

[0192] In an optional embodiment, the label corresponding to the first contour point set is of a first type; the label corresponding to the second contour point set is of a second type; the label corresponding to the third contour point set is of a first type; the first determining unit 5043 is specifically used for:

[0193] Based on the label corresponding to the first contour point set being of the first type, the state of each contour point in the first contour point set is determined as the first state; based on the label corresponding to the second contour point set being of the second type, the state of each contour point in the second contour point set is determined as the second state; the contour points in the first contour point set and their corresponding first states, and the contour points in the second contour point set and their corresponding second states, are combined to form a subset of drivable area contour points corresponding to the first ultrasonic radar.

[0194] In an optional embodiment, the first determining unit 5043 is specifically used for:

[0195] Based on the label corresponding to the first contour point set being of the first type, the state of each contour point in the first contour point set is determined as the first state; based on the label corresponding to the third contour point set being of the first type, the state of each contour point in the third contour point set is determined as the first state; the contour points in the first contour point set and their corresponding first states, and the contour points in the third contour point set and their corresponding first states, are combined to form a subset of drivable area contour points corresponding to the first ultrasonic radar.

[0196] In an optional embodiment, the apparatus of this disclosure further includes: a fifth processing module 601, configured to update the previously obtained ultrasonic grid map based on the set of contour points of the drivable area, to obtain an updated ultrasonic grid map.

[0197] In an optional embodiment, the fifth processing module 601 is specifically used for:

[0198] Based on the contour points in the drivable area contour point set and the corresponding states of each contour point, the state of the target grid in the ultrasonic grid map is determined. The states corresponding to the contour points include the first state and the second state. Based on the state of the target grid, the previously obtained ultrasonic grid map is updated to obtain the updated ultrasonic grid map.

[0199] The beneficial technical effects corresponding to the exemplary embodiments of this device can be found in the corresponding beneficial technical effects of the exemplary method section above, and will not be repeated here.

[0200] Exemplary electronic devices

[0201] Figure 16 This is a structural diagram of an electronic device provided in an embodiment of the present disclosure, including at least one processor 11 and a memory 12.

[0202] The processor 11 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0203] The memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may execute one or more computer program instructions to implement the methods and / or other desired functions of the various embodiments of this disclosure described above.

[0204] In one example, the electronic device 10 may also include an input device 13 and an output device 14, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0205] The input device 13 may also include, for example, a keyboard, a mouse, etc.

[0206] The output device 14 can output various information to the outside, including, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0207] Of course, for the sake of simplicity, Figure 16 Only some of the components of the electronic device 10 relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device 10 may include any other suitable components depending on the specific application.

[0208] Exemplary computer program products and computer-readable storage media

[0209] In addition to the methods and apparatus described above, embodiments of this disclosure may also provide a computer program product, including computer program instructions that, when executed by a processor, cause the processor to perform the steps of the methods in the various embodiments of this disclosure described in the "Exemplary Methods" section above.

[0210] Computer program products can be written in any combination of one or more programming languages ​​to perform the operations of embodiments of this disclosure. These programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0211] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps of the methods in the various embodiments of this disclosure described in the "Exemplary Methods" section above.

[0212] Computer-readable storage media may take the form of any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, but is not limited to, systems, apparatuses, or devices that are electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0213] The basic principles of this disclosure have been described above with reference to specific embodiments. However, the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0214] Various modifications and variations can be made to this disclosure without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this disclosure and their equivalents, this disclosure is also intended to include such modifications and variations.

Claims

1. A method for determining a drivable area, comprising: Acquire ultrasonic echo information corresponding to each of the ultrasonic radars in at least one ultrasonic radar, wherein the ultrasonic echo information includes echo signal and time information; Based on the ultrasonic echo information, determine the echo distance corresponding to each echo signal; Based on the echo distance corresponding to each echo signal, the current obstacle point set is determined; the current obstacle point set represents the obstacle boundary point set within the current sensing range of the ultrasonic radar. Based on the current set of obstacle points, determine the set of outline points for the drivable area; Based on the set of contour points of the drivable area, the drivable area is determined.

2. The method according to claim 1, wherein, The step of determining the current obstacle point set based on the echo distance corresponding to each of the echo signals includes: Based on the echo distance corresponding to each echo signal and the time information corresponding to each echo signal, an echo distance group belonging to the same obstacle point is determined. Each echo distance group includes a first echo distance and a second echo distance belonging to the same echo point. Based on the echo distance group belonging to the same obstacle point, determine the first obstacle point corresponding to the echo distance group; Based on the third echo distance in each echo distance group other than the echo distance group, determine the second obstacle point corresponding to the third echo distance; The current obstacle set is determined based on each of the first obstacle point and each of the second obstacle points.

3. The method according to claim 2, wherein, The step of determining the first obstacle point corresponding to the echo distance group based on the echo distance group belonging to the same obstacle point includes: For any of the echo distance groups, based on the first echo distance, the second echo distance, the first position of the ultrasonic radar corresponding to the first echo distance, and the second position of the ultrasonic radar corresponding to the second echo distance, the triangulation method is used to determine the first obstacle point corresponding to the echo distance group, where the first position and the second position are positions in the vehicle coordinate system.

4. The method according to claim 2, wherein, The step of determining the second obstacle point corresponding to the third echo distance based on the third echo distance other than the echo distance group in each of the echo distances includes: For any of the third echo distances, within the scanning range of the ultrasonic radar corresponding to the third echo distance, determine a line segment whose horizontal axis coordinate is the same as the third echo distance in the radar coordinate system of the ultrasonic radar. Based on a preset sampling rule, a first number of points are sampled on the line segment; The first number of points are transformed into the vehicle coordinate system to obtain the second obstacle point corresponding to the third echo distance.

5. The method according to claim 1, wherein, The step of determining the drivable area contour point set based on the current obstacle point set includes: Transform the current obstacle point set to the world coordinate system to obtain the target obstacle point set in the world coordinate system corresponding to the current obstacle point set. Based on the previous obstacle clustering results, incremental obstacle clustering is performed on the target obstacle point set to obtain a first point set corresponding to at least one target obstacle. The previous obstacle clustering results are the result of clustering based on the previously obtained obstacle point set. Based on the first set of points corresponding to each of the target obstacles, the set of points representing the drivable area is determined.

6. The method according to claim 5, wherein, Determining the drivable area contour point set based on the first point set corresponding to each of the target obstacles includes: For any of the first ultrasonic radars, in response to the first ultrasonic radar corresponding to at least one of the target obstacles, based on the first point set corresponding to each of the target obstacles corresponding to the first ultrasonic radar, the first side corner point and the second side corner point corresponding to each of the target obstacles are determined respectively. The first side corner point and the second side corner point corresponding to each of the target obstacles are respectively used as the first contour point set, and the label corresponding to the first contour point set is determined. Based on the first set of contour points and the corresponding labels of the first set of contour points, a subset of drivable area contour points corresponding to the first ultrasonic radar is determined. The drivable area contour point set is determined based on the subset of drivable area contour points corresponding to each of the ultrasonic radars.

7. The method according to claim 6, further comprising: For any of the first ultrasonic radars in the aforementioned ultrasonic radars, determine the positional relationship between the first ultrasonic radar and the other ultrasonic radars besides the first ultrasonic radar; In response to the first ultrasonic radar being located on the first or second side of each of the other ultrasonic radars, the set of scanning boundary points on the side of the first ultrasonic radar furthest from each of the other ultrasonic radars is taken as the second contour point set, and the label corresponding to the second contour point set is determined; or, In response to the first ultrasonic radar being located between at least two other ultrasonic radars and the existence of a first obstacle point with triangulation within the scanning range of the first ultrasonic radar, a first straight line passing through the first obstacle point and perpendicular to the normal of the field of view of the first ultrasonic radar is determined based on the first obstacle point. Based on the first straight line, determine the first intersection point between the first straight line and the normal of the field of view of the first ultrasonic radar, and the second intersection point between the first straight line and the scanning boundary of the first ultrasonic radar near the first obstacle point; The first intersection point and the second intersection point are used as the third contour point set, and the label corresponding to the third contour point set is determined. The step of determining the subset of drivable area contour points corresponding to the first ultrasonic radar based on the first contour point set and the labels corresponding to the first contour point set includes: Based on the first set of contour points, the labels corresponding to the first set of contour points, the second set of contour points, and the labels corresponding to the second set of contour points, a subset of drivable area contour points corresponding to the first ultrasonic radar is determined; or... Based on the first set of contour points, the label corresponding to the first set of contour points, the third set of contour points, and the label corresponding to the third set of contour points, the subset of contour points of the drivable area corresponding to the first ultrasonic radar is determined.

8. The method according to claim 7, wherein, The first set of contour points is labeled with a first type; the second set of contour points is labeled with a second type; and the third set of contour points is labeled with a first type. The step of determining the subset of drivable area contour points corresponding to the first ultrasonic radar based on the first contour point set, the labels corresponding to the first contour point set, the second contour point set, and the labels corresponding to the second contour point set includes: Based on the fact that the label corresponding to the first contour point set is of the first type, the state of each contour point in the first contour point set is determined to be the first state. Based on the fact that the label corresponding to the second contour point set is of the second type, the state of each contour point corresponding to the second contour point set is determined to be the second state. The contour points in the first contour point set and their corresponding first states, and the contour points in the second contour point set and their corresponding second states, are used to form the drivable area contour point subset corresponding to the first ultrasonic radar. The step of determining the subset of drivable area contour points corresponding to the first ultrasonic radar based on the first contour point set, the labels corresponding to the first contour point set, the third contour point set, and the labels corresponding to the third contour point set includes: Based on the fact that the label corresponding to the first contour point set is of the first type, the state of each contour point in the first contour point set is determined to be the first state. Based on the fact that the label corresponding to the third contour point set is of the first type, the state of each contour point corresponding to the third contour point set is determined to be the first state. The contour points in the first contour point set and their corresponding first states, and the contour points in the third contour point set and their corresponding first states, are used to form the drivable area contour point subset corresponding to the first ultrasonic radar.

9. The method according to claim 1, wherein, After determining the drivable area contour point set based on the current obstacle point set, the method further includes: Based on the set of contour points of the drivable area, the previously obtained ultrasonic grid map is updated to obtain an updated ultrasonic grid map.

10. The method according to claim 9, wherein, The step of updating the previously obtained ultrasonic raster map based on the drivable area contour point set to obtain an updated ultrasonic raster map includes: Based on each contour point in the set of contour points in the drivable area and the state corresponding to each contour point, the state of the target grid in the ultrasonic grid map is determined, and the state corresponding to the contour point includes a first state and a second state. Based on the state of the target grid, the previously obtained ultrasonic grid map is updated to obtain an updated ultrasonic grid map.

11. A device for determining a drivable area, comprising: The first acquisition module is used to acquire ultrasonic echo information corresponding to each of the ultrasonic radars in at least one ultrasonic radar, wherein the ultrasonic echo information includes echo signal and time information. The first processing module is used to determine the echo distance corresponding to each echo signal based on the ultrasonic echo information. The second processing module is used to determine the current obstacle point set based on the echo distance corresponding to each of the echo signals; the current obstacle point set represents the obstacle boundary point set within the current sensing range of the ultrasonic radar; The third processing module is used to determine the drivable area contour point set based on the current obstacle point set; The fourth processing module is used to determine the drivable area based on the set of drivable area contour points.

12. A computer-readable storage medium storing a computer program for performing the method for determining a drivable area as described in any one of claims 1-10.

13. An electronic device, the electronic device comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method for determining the drivable area as described in any one of claims 1-10.

Images